【阿旭机器学习实战】【36】糖尿病预测---决策树建模及其可视化

# 导入数据包
import pandas as pd
from sklearn.tree import DecisionTreeClassifier
from sklearn.model_selection import train_test_split 
from sklearn import metrics 
import matplotlib.pyplot as plt
import matplotlib as matplot
import seaborn as sns
%matplotlib inline

col_names = ['pregnant', 'glucose', 'bp', 'skin', 'insulin', 'bmi', 'pedigree', 'age', 'label']
df = pd.read_csv("pima-indians-diabetes.csv", header=None, names=col_names)

df.head()

# 相关性矩阵
corr = df.iloc[:,:-1].corr()
#corr = (corr)
sns.heatmap(corr, 
            xticklabels=corr.columns.values,
            yticklabels=corr.columns.values)
corr

# 选择预测所需的特征
feature_cols = ['pregnant', 'insulin', 'bmi', 'age','glucose','bp','pedigree']
X = pima[feature_cols] # 特征
y = pima.label # 类别标签

# 将数据分为训练和测试数据
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.3, random_state=1) # 70% training and 30% test

# 创建决策树分类器
clf = DecisionTreeClassifier(criterion='entropy')
# 训练模型
clf = clf.fit(X_train,y_train)
# 使用训练好的模型做预测
y_pred = clf.predict(X_test)

# 模型的准确性
print("Accuracy:",metrics.accuracy_score(y_test, y_pred))

Accuracy: 0.7489177489177489

from sklearn.tree import export_graphviz
from six import StringIO 
from IPython.display import Image  
import pydotplus
from sklearn import tree
dot_data = StringIO()
export_graphviz(clf, out_file=dot_data,  
                filled=True, rounded=True,
                special_characters=True,feature_names = feature_cols,class_names=['0','1'])
graph = pydotplus.graph_from_dot_data(dot_data.getvalue())  
graph.write_png('diabetes.png')
Image(graph.create_png())

# 创建新的决策树, 限定树的最大深度, 减少过拟合
clf = tree.DecisionTreeClassifier(
    criterion='entropy',
    max_depth=4, # 定义树的深度, 可以用来防止过拟合
    min_weight_fraction_leaf=0.01 # 定义叶子节点最少需要包含多少个样本(使用百分比表达), 防止过拟合
    )
# 训练模型
clf.fit(X_train,y_train)
# 预测
y_pred = clf.predict(X_test)
# 模型的性能
print("Accuracy:",metrics.accuracy_score(y_test, y_pred))

Accuracy: 0.7705627705627706

from six import StringIO  
from IPython.display import Image  
from sklearn.tree import export_graphviz
import pydotplus
dot_data = StringIO()
export_graphviz(clf, out_file=dot_data,  
                filled=True, rounded=True,
                special_characters=True, feature_names = feature_cols,class_names=['0','1'])
graph = pydotplus.graph_from_dot_data(dot_data.getvalue())  

graph.write_png('diabetes2.png')
Image(graph.create_png())

from sklearn.ensemble import RandomForestClassifier
# 随机森林, 通过调整参数来获取更好的结果
rf = RandomForestClassifier(
    criterion='entropy',
    n_estimators=1, 
    max_depth=5, # 定义树的深度, 可以用来防止过拟合
    min_samples_split=10, # 定义至少多少个样本的情况下才继续分叉
    #min_weight_fraction_leaf=0.02 # 定义叶子节点最少需要包含多少个样本(使用百分比表达), 防止过拟合
    )
# 训练模型
rf.fit(X_train, y_train)
# 做预测
y_pred = rf.predict(X_test)
# 模型的准确率
print("Accuracy:",metrics.accuracy_score(y_test, y_pred))

Accuracy: 0.7402597402597403